LLM Reference

Baichuan M2 32B on Novita AI

Baichuan M2 · Baichuan Intelligent Technology

ServerlessOpen Source

Last refreshed 2026-05-22. Next refresh: weekly.

Why use Baichuan M2 32B on Novita AI?

Novita AI offers Baichuan M2 32B with pay-as-you-go pricing at $0.07/1M input tokens. Novita AI offers a GPU-based inference API for image, video, and language model generation with a broad catalog of open-source models.

Input / 1M
$0.070
Output / 1M
$0.070
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: baichuan-m2-32b
Model ID
baichuan-m2-32b

Request example

Curated snippets for this provider have not been sourced yet.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Pricing

TypePrice (per 1M)
Input tokens$0.07
Output tokens$0.07

Capabilities

Reasoning

About Baichuan M2 32B

Baichuan M2 32B is Baichuan AI's second medical-enhanced reasoning model, built upon Qwen2.5-32B with an innovative Large Verifier System. Trained via multi-stage reinforcement learning with improved GRPO for real-world medical reasoning tasks including diagnosis, treatment planning, and clinical Q&A. Outperforms all open-source models and most closed-source counterparts on HealthBench. Released with arXiv paper 2509.02208.

FAQ

What does Baichuan M2 32B cost on Novita AI?

On Novita AI, Baichuan M2 32B costs $0.07 per 1M input tokens and $0.07 per 1M output tokens.

What is the context window for Baichuan M2 32B on Novita AI?

Baichuan M2 32B supports a 131,072 token context window on Novita AI.

What API model ID do I use for Baichuan M2 32B on Novita AI?

Use the model ID baichuan-m2-32b when calling Novita AI's API.

Who created Baichuan M2 32B?

Baichuan M2 32B was created by Baichuan Intelligent Technology as part of the Baichuan M2 model family.

Is Baichuan M2 32B open source?

Baichuan M2 32B is open source according to the seed data.

Get Started

Model Specs

Released2025-09-02
Parameters32B
Context131K
ArchitectureDecoder Only